Skip to content
How to Use AI to Survive (and Even Enjoy) Meetings | Sam Stephenson artwork

How to Use AI to Survive (and Even Enjoy) Meetings | Sam Stephenson

Behind the Craft

October 4, 2026

Sam is the co-founder of Granola, the AI meeting notes app now valued at $1.5B. Granola has helped me survive (and even enjoy) countless meetings, so I was excited to learn how Sam uses AI to show up prepared.

Speakers Sam Stephenson, Peter Yang

TopicsTechnology

Sam Stephenson (0:00)

I think the number one feeling we want people to feel is calm when they use Granola. The main time we hold it in our heads is we're thinking about the product is like the messy in-between moments between back-to-back meetings. You're probably running late, probably forgot who you're going to be speaking to. We want to be a calming presence in your life.

Peter Yang (0:14)

You know what would be the ultimate future request from me? I'll have a Peter agent and you have a Sam agent, and then we go send our agents to have a meeting first to align. If they can't align, then we come in.

Sam Stephenson (0:22)

We get a lot of CEOs asking for that kind of thing. Can you make Granola be my first line of defense from all the questions I get all the time?

Peter Yang (0:31)

All right, hey, everyone. Today, I'm very excited to welcome Sam, the co-founder of Granola. Granola started as an AI meeting notes tool, and now they're worth $1.5 billion. So I actually really want to get Sam to show us how he personally uses Granola beyond meeting notes, and also how Granola runs internally using agents. So welcome, Sam.

Sam Stephenson (0:48)

Thank you, Peter. Nice to be here. I've been looking forward to this.

Peter Yang (0:51)

Why don't we get right into it? I think most people use Granola just to take meetings with AI, but I'm curious how you personally use Granola. Can you show us your personal Granola setup?

Sam Stephenson (0:59)

I've become very dependent on these pre-meeting briefs. I find these most useful. I've kind of under-prepared for a meeting with somebody new, like often like a new candidate.

I do a lot of cultural interviews as part of the hiring process, and if I'm not up to speed on who the candidate is I'm talking to, it saves my ass and embarrasses me a lot of times.

Peter Yang (1:18)

Nice.

Sam Stephenson (1:18)

And yeah, it was a bunch of work to make this just the right information that you need right as you're going into the meeting, but I feel kind of naked without them now if I'm meeting something new.

Peter Yang (1:27)

I think it will be next level if Granola can actually help suss out disagreements that people are not expressing. And then be like, actually, Sam and Peter, do you guys actually agree on this thing during the meeting?

Sam Stephenson (1:39)

So one of our investors has a really good recipe, which is designed to run after the meeting, not really during the meeting, but he uses this a lot, I think, after meetings to go back and do a post-match analysis and figure out, what did I miss? What should I have asked? How could I have gone deeper during that conversation? Yeah, I think that kind of thing is really powerful. Like our sales team will do this as well on a sales call.

After the meeting, they'll be like, what should I have done better that time, Granola? And it has the history of previous sales calls you've done, and so it can sometimes give a pretty smart answer there.

Peter Yang (2:17)

Got it. Do you just take some notes here and then Granola fills in the rest of the notes, and then you apply a recipe to it afterwards, like you apply some sort of temperate to it afterwards?

Sam Stephenson (2:26)

For me, the automatic notes sorts me out 95% of the time. The things I will use recipes and stuff for is I use this what did I miss thing a lot. Like if I'm, I shouldn't be, but if I'm in the multitasking during the meeting, or zone out thinking about something else, I'll be reaching for this to get me back on track. We're talking about making this more of a prototype feature.

You have this numbs thing over here, which has a live transcript, and I want to just make it so that you hover over this, we tell you what you missed straight away. Because it's by far the most used recipe that people could come to see all the time.

Peter Yang (3:08)

Yeah. I don't know if I should admit this, but sometimes I meet with a candidate for product too, and they give me an answer, and then I probably should not admit this, but I like to double-check with Granola, and be like, hey, this is a good answer. Like, what is he saying?

Sam Stephenson (3:21)

Yeah.

Peter Yang (3:22)

Especially if you give it a pretty good template beforehand of the rubric that you're trying to assess, it's actually pretty good.

33 more minutes of transcript below

Thousands of transcripts fetched by people building searchable podcast archives

Fetch the whole transcript

The demo key returns a sample episode in full, no card needed:

request
curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.

From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.

Using your own key:

request
curl -H "x-api-key: YOUR_KEY" \
  https://spoken.md/transcripts/1000793102828